Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) - Jetson Orin Nano Dev kit
• DeepStream Version 7.2
• JetPack Version (valid for Jetson only) latest
• TensorRT Version latest
• NVIDIA GPU Driver Version (valid for GPU only) latest
• Issue Type( questions, new requirements, bugs)
I am testing the NvDCF tracker with reid typet set for reassociation, I downloaded the sample model from the link in the deepStream documentation, and for every time i start my pipeline it re-creates the .engine model file, even tho I have the corect path to the .engine file set on my tracker config.
below is the terminal output of my pipeline:
”airis@ubuntu:~/Desktop/AirisInference/production$ python3 -m main.main_deepStream
pygame-ce 2.5.2 (SDL 2.30.8, Python 3.10.12)
/usr/lib/python3/dist-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.17.3 and <1.25.0 is required for this version of SciPy (detected version 1.26.0
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
Found non-empty last state file: /tmp/last_state_temp.txt
SGIEs: False, Display: False
Starting DS pipeline
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
~~ CLOG[/dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/src/modules/ReID/ReID.cpp, loadTRTEngine() @line 552]: Engine file does not exist
[NvMultiObjectTracker] Load engine failed. Create engine again.
WARNING: INT8 calibration file not specified. Trying FP16 mode.
WARNING: [TRT]: DLA requests all profiles have same min, max, and opt value. All dla layers are falling back to GPU
ERROR: [TRT]: IRuntime::~IRuntime: Error Code 3: API Usage Error (Parameter check failed, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.)
[NvMultiObjectTracker] Serialized plan file cached at location: /opt/nvidia/deepstream/deepstream-7.1/samples/models/Tracker/resnet50_market1501.etlt_b100_gpu0_fp16.engine
[NvMultiObjectTracker] Initialized
Setting min object dimensions as 16x16 instead of 1x1 to support VIC compute mode.
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:15:13.976841549 48713 0xaaaaeca35c60 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2092> [UID = 1]: deserialized trt engine from :/home/airis/Desktop/iago/sistemas/inference/models/model_b1_gpu0_fp16.engine
Implicit layer support has been deprecated
INFO: [Implicit Engine Info]: layers num: 0
0:15:13.976947856 48713 0xaaaaeca35c60 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2195> [UID = 1]: Use deserialized engine model: /home/airis/Desktop/iago/sistemas/inference/models/model_b1_gpu0_fp16.engine
0:15:13.992331015 48713 0xaaaaeca35c60 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus: [UID 1]: Load new model:/home/airis/Desktop/iago/sistemas/inference/models/dslaunchpad_pgie_config.txt sucessfully
Opening in BLOCKING MODE
NvMMLiteOpen : Block : BlockType = 261
NvMMLiteBlockCreate : Block : BlockType = 261
nvstreammux: Successfully handled EOS for source_id=0”
it takes about 15 to create a .engine
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
Run a sample deepStream pipeline, single video input, with the NvDCF tracker with its default configs.
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)